{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:34Z","timestamp":1777888714381,"version":"3.51.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01056","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11348-11358","source":"Crossref","is-referenced-by-count":0,"title":["Punching Bag vs. Punching Person: Motion Transferability in Videos"],"prefix":"10.1109","author":[{"given":"Raiyaan","family":"Abdullah","sequence":"first","affiliation":[{"name":"University of Central Florida,Center for Research in Computer Vision"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jared","family":"Claypoole","sequence":"additional","affiliation":[{"name":"SRI International,Center for Vision Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Cogswell","sequence":"additional","affiliation":[{"name":"SRI International,Center for Vision Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajay","family":"Divakaran","sequence":"additional","affiliation":[{"name":"SRI International,Center for Vision Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yogesh","family":"Rawat","sequence":"additional","affiliation":[{"name":"University of Central Florida,Center for Research in Computer Vision"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Ahmad","year":"2024","journal-title":"Ezclip: Efficient zeroshot video action recognition"},{"key":"ref2","article-title":"T21: Efficient zero-shot action recognition with temporal token learning","author":"Ahmad","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91581-9_4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00346"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00799"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00642"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6247-8_1394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00092"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412541"},{"key":"ref13","author":"Dosovitskiy","year":"2021","journal-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale"},{"key":"ref14","first-page":"7621","article-title":"Videocapsulenet: a simplified network for action detection","volume-title":"Proceedings of the 32nd International Conference on Neural In-formation Processing Systems","author":"Duarte"},{"key":"ref15","volume-title":"Pyslowfast","author":"Fan","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92659-5_12"},{"key":"ref21","article-title":"something something","author":"Goyal","year":"2017","journal-title":"video database for learning and evaluating visual common sense"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref25","author":"Huang","year":"2024","journal-title":"Froster: Frozen clip is a strong teacher for open-vocabulary action recognition"},{"key":"ref26","author":"Kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref27","first-page":"25566","article-title":"Reformulating zero-shot action recognition for multilabel actions","author":"Kerrigan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"ref29","author":"Li","year":"2022","journal-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning"},{"key":"ref30","author":"Li","year":"2022","journal-title":"Uniformerv2: Spatiotemporal learning by arming image vits with video uniformer"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref33","author":"Lin","year":"2022","journal-title":"Cross-modal representation learning for zeroshot action recognition"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2443"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01056"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00538"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01950"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01998-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01256"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_7"},{"key":"ref46","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_8"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00186"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01412"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490580"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.84"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28290"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00966"},{"key":"ref55","article-title":"Learning That Transfers: Designing Curriculum for a Changing World","author":"Stern","year":"2021","journal-title":"Corwin"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref57","author":"Wang","year":"2021","journal-title":"Actionclip: A new paradigm for video action recognition"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_21"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-75640-6"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350760"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01431"},{"key":"ref63","author":"Yang","year":"2023","journal-title":"Aim: Adapting image models for efficient video action recognition"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3116945"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01213"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1137"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.280"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01896"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444946.pdf?arnumber=11444946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:53Z","timestamp":1777611293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444946\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01056","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}